Upload folder using huggingface_hub

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

README.md

@@ -1,3 +1,202 @@
----
-license: mit
----
+---
+base_model: Qwen/Qwen3-32B
+library_name: peft
+---
+
+# Model Card for Model ID
+
+<!-- Provide a quick summary of what the model is/does. -->
+
+
+
+## Model Details
+
+### Model Description
+
+<!-- Provide a longer summary of what this model is. -->
+
+
+
+- **Developed by:** [More Information Needed]
+- **Funded by [optional]:** [More Information Needed]
+- **Shared by [optional]:** [More Information Needed]
+- **Model type:** [More Information Needed]
+- **Language(s) (NLP):** [More Information Needed]
+- **License:** [More Information Needed]
+- **Finetuned from model [optional]:** [More Information Needed]
+
+### Model Sources [optional]
+
+<!-- Provide the basic links for the model. -->
+
+- **Repository:** [More Information Needed]
+- **Paper [optional]:** [More Information Needed]
+- **Demo [optional]:** [More Information Needed]
+
+## Uses
+
+<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
+
+### Direct Use
+
+<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
+
+[More Information Needed]
+
+### Downstream Use [optional]
+
+<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
+
+[More Information Needed]
+
+### Out-of-Scope Use
+
+<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
+
+[More Information Needed]
+
+## Bias, Risks, and Limitations
+
+<!-- This section is meant to convey both technical and sociotechnical limitations. -->
+
+[More Information Needed]
+
+### Recommendations
+
+<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
+
+Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
+
+## How to Get Started with the Model
+
+Use the code below to get started with the model.
+
+[More Information Needed]
+
+## Training Details
+
+### Training Data
+
+<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
+
+[More Information Needed]
+
+### Training Procedure
+
+<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
+
+#### Preprocessing [optional]
+
+[More Information Needed]
+
+
+#### Training Hyperparameters
+
+- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
+
+#### Speeds, Sizes, Times [optional]
+
+<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
+
+[More Information Needed]
+
+## Evaluation
+
+<!-- This section describes the evaluation protocols and provides the results. -->
+
+### Testing Data, Factors & Metrics
+
+#### Testing Data
+
+<!-- This should link to a Dataset Card if possible. -->
+
+[More Information Needed]
+
+#### Factors
+
+<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
+
+[More Information Needed]
+
+#### Metrics
+
+<!-- These are the evaluation metrics being used, ideally with a description of why. -->
+
+[More Information Needed]
+
+### Results
+
+[More Information Needed]
+
+#### Summary
+
+
+
+## Model Examination [optional]
+
+<!-- Relevant interpretability work for the model goes here -->
+
+[More Information Needed]
+
+## Environmental Impact
+
+<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
+
+Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
+
+- **Hardware Type:** [More Information Needed]
+- **Hours used:** [More Information Needed]
+- **Cloud Provider:** [More Information Needed]
+- **Compute Region:** [More Information Needed]
+- **Carbon Emitted:** [More Information Needed]
+
+## Technical Specifications [optional]
+
+### Model Architecture and Objective
+
+[More Information Needed]
+
+### Compute Infrastructure
+
+[More Information Needed]
+
+#### Hardware
+
+[More Information Needed]
+
+#### Software
+
+[More Information Needed]
+
+## Citation [optional]
+
+<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
+
+**BibTeX:**
+
+[More Information Needed]
+
+**APA:**
+
+[More Information Needed]
+
+## Glossary [optional]
+
+<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
+
+[More Information Needed]
+
+## More Information [optional]
+
+[More Information Needed]
+
+## Model Card Authors [optional]
+
+[More Information Needed]
+
+## Model Card Contact
+
+[More Information Needed]
+### Framework versions
+
+- PEFT 0.15.1

adapter_config.json

@@ -0,0 +1,39 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "Qwen/Qwen3-32B",
+  "bias": "none",
+  "corda_config": null,
+  "eva_config": null,
+  "exclude_modules": [],
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 128,
+  "lora_bias": false,
+  "lora_dropout": 0.0,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 64,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "v_proj",
+    "down_proj",
+    "gate_proj",
+    "o_proj",
+    "up_proj",
+    "q_proj",
+    "k_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_rslora": false
+}

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e5aa00f231f1e281a73a1f6228dbaee2e18bb9b7b0810ac6fe16eb96b5940414
+size 2147605960

added_tokens.json

@@ -0,0 +1,28 @@
+{
+  "</think>": 151668,
+  "</tool_call>": 151658,
+  "</tool_response>": 151666,
+  "<think>": 151667,
+  "<tool_call>": 151657,
+  "<tool_response>": 151665,
+  "<|box_end|>": 151649,
+  "<|box_start|>": 151648,
+  "<|endoftext|>": 151643,
+  "<|file_sep|>": 151664,
+  "<|fim_middle|>": 151660,
+  "<|fim_pad|>": 151662,
+  "<|fim_prefix|>": 151659,
+  "<|fim_suffix|>": 151661,
+  "<|im_end|>": 151645,
+  "<|im_start|>": 151644,
+  "<|image_pad|>": 151655,
+  "<|object_ref_end|>": 151647,
+  "<|object_ref_start|>": 151646,
+  "<|quad_end|>": 151651,
+  "<|quad_start|>": 151650,
+  "<|repo_name|>": 151663,
+  "<|video_pad|>": 151656,
+  "<|vision_end|>": 151653,
+  "<|vision_pad|>": 151654,
+  "<|vision_start|>": 151652
+}

chat_template.jinja

@@ -0,0 +1,89 @@
+{%- if tools %}
+    {{- '<|im_start|>system\n' }}
+    {%- if messages[0].role == 'system' %}
+        {{- messages[0].content + '\n\n' }}
+    {%- endif %}
+    {{- "# Tools\n\nYou may call one or more functions to assist with the user query.\n\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>" }}
+    {%- for tool in tools %}
+        {{- "\n" }}
+        {{- tool | tojson }}
+    {%- endfor %}
+    {{- "\n</tools>\n\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\n<tool_call>\n{\"name\": <function-name>, \"arguments\": <args-json-object>}\n</tool_call><|im_end|>\n" }}
+{%- else %}
+    {%- if messages[0].role == 'system' %}
+        {{- '<|im_start|>system\n' + messages[0].content + '<|im_end|>\n' }}
+    {%- endif %}
+{%- endif %}
+{%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}
+{%- for message in messages[::-1] %}
+    {%- set index = (messages|length - 1) - loop.index0 %}
+    {%- if ns.multi_step_tool and message.role == "user" and message.content is string and not(message.content.startswith('<tool_response>') and message.content.endswith('</tool_response>')) %}
+        {%- set ns.multi_step_tool = false %}
+        {%- set ns.last_query_index = index %}
+    {%- endif %}
+{%- endfor %}
+{%- for message in messages %}
+    {%- if message.content is string %}
+        {%- set content = message.content %}
+    {%- else %}
+        {%- set content = '' %}
+    {%- endif %}
+    {%- if (message.role == "user") or (message.role == "system" and not loop.first) %}
+        {{- '<|im_start|>' + message.role + '\n' + content + '<|im_end|>' + '\n' }}
+    {%- elif message.role == "assistant" %}
+        {%- set reasoning_content = '' %}
+        {%- if message.reasoning_content is string %}
+            {%- set reasoning_content = message.reasoning_content %}
+        {%- else %}
+            {%- if '</think>' in content %}
+                {%- set reasoning_content = content.split('</think>')[0].rstrip('\n').split('<think>')[-1].lstrip('\n') %}
+                {%- set content = content.split('</think>')[-1].lstrip('\n') %}
+            {%- endif %}
+        {%- endif %}
+        {%- if loop.index0 > ns.last_query_index %}
+            {%- if loop.last or (not loop.last and reasoning_content) %}
+                {{- '<|im_start|>' + message.role + '\n<think>\n' + reasoning_content.strip('\n') + '\n</think>\n\n' + content.lstrip('\n') }}
+            {%- else %}
+                {{- '<|im_start|>' + message.role + '\n' + content }}
+            {%- endif %}
+        {%- else %}
+            {{- '<|im_start|>' + message.role + '\n' + content }}
+        {%- endif %}
+        {%- if message.tool_calls %}
+            {%- for tool_call in message.tool_calls %}
+                {%- if (loop.first and content) or (not loop.first) %}
+                    {{- '\n' }}
+                {%- endif %}
+                {%- if tool_call.function %}
+                    {%- set tool_call = tool_call.function %}
+                {%- endif %}
+                {{- '<tool_call>\n{"name": "' }}
+                {{- tool_call.name }}
+                {{- '", "arguments": ' }}
+                {%- if tool_call.arguments is string %}
+                    {{- tool_call.arguments }}
+                {%- else %}
+                    {{- tool_call.arguments | tojson }}
+                {%- endif %}
+                {{- '}\n</tool_call>' }}
+            {%- endfor %}
+        {%- endif %}
+        {{- '<|im_end|>\n' }}
+    {%- elif message.role == "tool" %}
+        {%- if loop.first or (messages[loop.index0 - 1].role != "tool") %}
+            {{- '<|im_start|>user' }}
+        {%- endif %}
+        {{- '\n<tool_response>\n' }}
+        {{- content }}
+        {{- '\n</tool_response>' }}
+        {%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
+            {{- '<|im_end|>\n' }}
+        {%- endif %}
+    {%- endif %}
+{%- endfor %}
+{%- if add_generation_prompt %}
+    {{- '<|im_start|>assistant\n' }}
+    {%- if enable_thinking is defined and enable_thinking is false %}
+        {{- '<think>\n\n</think>\n\n' }}
+    {%- endif %}
+{%- endif %}

config.json

@@ -0,0 +1,97 @@
+{
+  "architectures": [
+    "Qwen3ForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "dtype": "bfloat16",
+  "eos_token_id": 151645,
+  "head_dim": 128,
+  "hidden_act": "silu",
+  "hidden_size": 5120,
+  "initializer_range": 0.02,
+  "intermediate_size": 25600,
+  "layer_types": [
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention"
+  ],
+  "max_position_embeddings": 40960,
+  "max_window_layers": 64,
+  "model_type": "qwen3",
+  "num_attention_heads": 64,
+  "num_hidden_layers": 64,
+  "num_key_value_heads": 8,
+  "pad_token_id": 151643,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 1000000,
+  "sliding_window": null,
+  "tie_word_embeddings": false,
+  "transformers_version": "4.57.0",
+  "use_cache": false,
+  "use_sliding_window": false,
+  "vocab_size": 151936,
+  "torch_dtype": "bfloat16"
+}

special_tokens_map.json

@@ -0,0 +1,31 @@
+{
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "eos_token": {
+    "content": "<|im_end|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:aeb13307a71acd8fe81861d94ad54ab689df773318809eed3cbe794b4492dae4
+size 11422654

tokenizer_config.json

@@ -0,0 +1,240 @@
+{
+  "add_bos_token": false,
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "151643": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151644": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151645": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151646": {
+      "content": "<|object_ref_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151647": {
+      "content": "<|object_ref_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151648": {
+      "content": "<|box_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151649": {
+      "content": "<|box_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151650": {
+      "content": "<|quad_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151651": {
+      "content": "<|quad_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151652": {
+      "content": "<|vision_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151653": {
+      "content": "<|vision_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151654": {
+      "content": "<|vision_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151655": {
+      "content": "<|image_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151656": {
+      "content": "<|video_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151657": {
+      "content": "<tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151658": {
+      "content": "</tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151659": {
+      "content": "<|fim_prefix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151660": {
+      "content": "<|fim_middle|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151661": {
+      "content": "<|fim_suffix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151662": {
+      "content": "<|fim_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151663": {
+      "content": "<|repo_name|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151664": {
+      "content": "<|file_sep|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151665": {
+      "content": "<tool_response>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151666": {
+      "content": "</tool_response>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151667": {
+      "content": "<think>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151668": {
+      "content": "</think>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    }
+  },
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "bos_token": null,
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "extra_special_tokens": {},
+  "model_max_length": 131072,
+  "pad_token": "<|endoftext|>",
+  "padding_side": "right",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

trainer_state.json

@@ -0,0 +1,483 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 3.0,
+  "eval_steps": 63,
+  "global_step": 63,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.047619047619047616,
+      "grad_norm": 0.4443244934082031,
+      "learning_rate": 0.0,
+      "loss": 1.7686,
+      "step": 1
+    },
+    {
+      "epoch": 0.09523809523809523,
+      "grad_norm": 0.40687671303749084,
+      "learning_rate": 5e-05,
+      "loss": 1.6323,
+      "step": 2
+    },
+    {
+      "epoch": 0.14285714285714285,
+      "grad_norm": 0.30237045884132385,
+      "learning_rate": 0.0001,
+      "loss": 1.5591,
+      "step": 3
+    },
+    {
+      "epoch": 0.19047619047619047,
+      "grad_norm": 0.15168103575706482,
+      "learning_rate": 0.00015000000000000001,
+      "loss": 1.2163,
+      "step": 4
+    },
+    {
+      "epoch": 0.23809523809523808,
+      "grad_norm": 0.12413862347602844,
+      "learning_rate": 0.0002,
+      "loss": 1.0686,
+      "step": 5
+    },
+    {
+      "epoch": 0.2857142857142857,
+      "grad_norm": 0.10256382077932358,
+      "learning_rate": 0.0001998724426109086,
+      "loss": 0.9393,
+      "step": 6
+    },
+    {
+      "epoch": 0.3333333333333333,
+      "grad_norm": 0.12325788289308548,
+      "learning_rate": 0.00019949013201891235,
+      "loss": 1.0493,
+      "step": 7
+    },
+    {
+      "epoch": 0.38095238095238093,
+      "grad_norm": 0.10104131698608398,
+      "learning_rate": 0.00019885415192492104,
+      "loss": 0.8018,
+      "step": 8
+    },
+    {
+      "epoch": 0.42857142857142855,
+      "grad_norm": 0.08828374743461609,
+      "learning_rate": 0.000197966305083608,
+      "loss": 0.8639,
+      "step": 9
+    },
+    {
+      "epoch": 0.47619047619047616,
+      "grad_norm": 0.07189645618200302,
+      "learning_rate": 0.00019682910819330646,
+      "loss": 0.9037,
+      "step": 10
+    },
+    {
+      "epoch": 0.5238095238095238,
+      "grad_norm": 0.07045362889766693,
+      "learning_rate": 0.0001954457847621543,
+      "loss": 0.8889,
+      "step": 11
+    },
+    {
+      "epoch": 0.5714285714285714,
+      "grad_norm": 0.05801837518811226,
+      "learning_rate": 0.00019382025597071049,
+      "loss": 0.7699,
+      "step": 12
+    },
+    {
+      "epoch": 0.6190476190476191,
+      "grad_norm": 0.06970051676034927,
+      "learning_rate": 0.0001919571295569422,
+      "loss": 0.9115,
+      "step": 13
+    },
+    {
+      "epoch": 0.6666666666666666,
+      "grad_norm": 0.0628025084733963,
+      "learning_rate": 0.00018986168675509145,
+      "loss": 0.7743,
+      "step": 14
+    },
+    {
+      "epoch": 0.7142857142857143,
+      "grad_norm": 0.06034975126385689,
+      "learning_rate": 0.00018753986732544255,
+      "loss": 0.8773,
+      "step": 15
+    },
+    {
+      "epoch": 0.7619047619047619,
+      "grad_norm": 0.06134900078177452,
+      "learning_rate": 0.00018499825271742635,
+      "loss": 0.8964,
+      "step": 16
+    },
+    {
+      "epoch": 0.8095238095238095,
+      "grad_norm": 0.0681927427649498,
+      "learning_rate": 0.00018224404741378674,
+      "loss": 0.7794,
+      "step": 17
+    },
+    {
+      "epoch": 0.8571428571428571,
+      "grad_norm": 0.04857668653130531,
+      "learning_rate": 0.00017928505850869157,
+      "loss": 0.8812,
+      "step": 18
+    },
+    {
+      "epoch": 0.9047619047619048,
+      "grad_norm": 0.09804921597242355,
+      "learning_rate": 0.00017612967357767605,
+      "loss": 0.6323,
+      "step": 19
+    },
+    {
+      "epoch": 0.9523809523809523,
+      "grad_norm": 0.100680872797966,
+      "learning_rate": 0.00017278683690214865,
+      "loss": 0.4672,
+      "step": 20
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 0.06439036875963211,
+      "learning_rate": 0.0001692660241158535,
+      "loss": 0.6914,
+      "step": 21
+    },
+    {
+      "epoch": 1.0476190476190477,
+      "grad_norm": 0.09892687946557999,
+      "learning_rate": 0.0001655772153451573,
+      "loss": 0.7493,
+      "step": 22
+    },
+    {
+      "epoch": 1.0952380952380953,
+      "grad_norm": 0.06118744984269142,
+      "learning_rate": 0.00016173086691929664,
+      "loss": 0.6816,
+      "step": 23
+    },
+    {
+      "epoch": 1.1428571428571428,
+      "grad_norm": 0.05294615402817726,
+      "learning_rate": 0.00015773788173077682,
+      "loss": 0.778,
+      "step": 24
+    },
+    {
+      "epoch": 1.1904761904761905,
+      "grad_norm": 0.05229621380567551,
+      "learning_rate": 0.00015360957832993852,
+      "loss": 0.7626,
+      "step": 25
+    },
+    {
+      "epoch": 1.2380952380952381,
+      "grad_norm": 0.05765673518180847,
+      "learning_rate": 0.000149357658841297,
+      "loss": 0.6942,
+      "step": 26
+    },
+    {
+      "epoch": 1.2857142857142856,
+      "grad_norm": 0.05352270230650902,
+      "learning_rate": 0.0001449941757925989,
+      "loss": 0.6517,
+      "step": 27
+    },
+    {
+      "epoch": 1.3333333333333333,
+      "grad_norm": 0.05008169636130333,
+      "learning_rate": 0.00014053149795062274,
+      "loss": 0.8101,
+      "step": 28
+    },
+    {
+      "epoch": 1.380952380952381,
+      "grad_norm": 0.06564240157604218,
+      "learning_rate": 0.0001359822752605659,
+      "loss": 0.5362,
+      "step": 29
+    },
+    {
+      "epoch": 1.4285714285714286,
+      "grad_norm": 0.05252636596560478,
+      "learning_rate": 0.00013135940298840035,
+      "loss": 0.6523,
+      "step": 30
+    },
+    {
+      "epoch": 1.4761904761904763,
+      "grad_norm": 0.057543374598026276,
+      "learning_rate": 0.0001266759851678403,
+      "loss": 0.6996,
+      "step": 31
+    },
+    {
+      "epoch": 1.5238095238095237,
+      "grad_norm": 0.05740825831890106,
+      "learning_rate": 0.00012194529745553497,
+      "loss": 0.6906,
+      "step": 32
+    },
+    {
+      "epoch": 1.5714285714285714,
+      "grad_norm": 0.06167572736740112,
+      "learning_rate": 0.00011718074949977748,
+      "loss": 0.5829,
+      "step": 33
+    },
+    {
+      "epoch": 1.619047619047619,
+      "grad_norm": 0.0648028552532196,
+      "learning_rate": 0.00011239584692939975,
+      "loss": 0.7389,
+      "step": 34
+    },
+    {
+      "epoch": 1.6666666666666665,
+      "grad_norm": 0.06073867157101631,
+      "learning_rate": 0.00010760415307060027,
+      "loss": 0.6082,
+      "step": 35
+    },
+    {
+      "epoch": 1.7142857142857144,
+      "grad_norm": 0.06266023218631744,
+      "learning_rate": 0.00010281925050022251,
+      "loss": 0.7021,
+      "step": 36
+    },
+    {
+      "epoch": 1.7619047619047619,
+      "grad_norm": 0.059252478182315826,
+      "learning_rate": 9.805470254446503e-05,
+      "loss": 0.7452,
+      "step": 37
+    },
+    {
+      "epoch": 1.8095238095238095,
+      "grad_norm": 0.07034861296415329,
+      "learning_rate": 9.332401483215973e-05,
+      "loss": 0.5951,
+      "step": 38
+    },
+    {
+      "epoch": 1.8571428571428572,
+      "grad_norm": 0.06802237033843994,
+      "learning_rate": 8.864059701159965e-05,
+      "loss": 0.7478,
+      "step": 39
+    },
+    {
+      "epoch": 1.9047619047619047,
+      "grad_norm": 0.06658069789409637,
+      "learning_rate": 8.401772473943415e-05,
+      "loss": 0.4647,
+      "step": 40
+    },
+    {
+      "epoch": 1.9523809523809523,
+      "grad_norm": 0.06517181545495987,
+      "learning_rate": 7.946850204937728e-05,
+      "loss": 0.3225,
+      "step": 41
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 0.07028491795063019,
+      "learning_rate": 7.500582420740115e-05,
+      "loss": 0.5495,
+      "step": 42
+    },
+    {
+      "epoch": 2.0476190476190474,
+      "grad_norm": 0.0754581019282341,
+      "learning_rate": 7.064234115870303e-05,
+      "loss": 0.569,
+      "step": 43
+    },
+    {
+      "epoch": 2.0952380952380953,
+      "grad_norm": 0.07950273901224136,
+      "learning_rate": 6.63904216700615e-05,
+      "loss": 0.5266,
+      "step": 44
+    },
+    {
+      "epoch": 2.142857142857143,
+      "grad_norm": 0.06878385692834854,
+      "learning_rate": 6.226211826922319e-05,
+      "loss": 0.636,
+      "step": 45
+    },
+    {
+      "epoch": 2.1904761904761907,
+      "grad_norm": 0.06523990631103516,
+      "learning_rate": 5.8269133080703386e-05,
+      "loss": 0.633,
+      "step": 46
+    },
+    {
+      "epoch": 2.238095238095238,
+      "grad_norm": 0.07029258459806442,
+      "learning_rate": 5.442278465484274e-05,
+      "loss": 0.5476,
+      "step": 47
+    },
+    {
+      "epoch": 2.2857142857142856,
+      "grad_norm": 0.06552315503358841,
+      "learning_rate": 5.0733975884146533e-05,
+      "loss": 0.5169,
+      "step": 48
+    },
+    {
+      "epoch": 2.3333333333333335,
+      "grad_norm": 0.06902378797531128,
+      "learning_rate": 4.721316309785139e-05,
+      "loss": 0.6818,
+      "step": 49
+    },
+    {
+      "epoch": 2.380952380952381,
+      "grad_norm": 0.07481586933135986,
+      "learning_rate": 4.387032642232397e-05,
+      "loss": 0.3834,
+      "step": 50
+    },
+    {
+      "epoch": 2.4285714285714284,
+      "grad_norm": 0.0717826560139656,
+      "learning_rate": 4.071494149130843e-05,
+      "loss": 0.5264,
+      "step": 51
+    },
+    {
+      "epoch": 2.4761904761904763,
+      "grad_norm": 0.07843846827745438,
+      "learning_rate": 3.775595258621329e-05,
+      "loss": 0.5632,
+      "step": 52
+    },
+    {
+      "epoch": 2.5238095238095237,
+      "grad_norm": 0.07552829384803772,
+      "learning_rate": 3.500174728257365e-05,
+      "loss": 0.5551,
+      "step": 53
+    },
+    {
+      "epoch": 2.571428571428571,
+      "grad_norm": 0.07394373416900635,
+      "learning_rate": 3.246013267455745e-05,
+      "loss": 0.458,
+      "step": 54
+    },
+    {
+      "epoch": 2.619047619047619,
+      "grad_norm": 0.07493584603071213,
+      "learning_rate": 3.0138313244908573e-05,
+      "loss": 0.6155,
+      "step": 55
+    },
+    {
+      "epoch": 2.6666666666666665,
+      "grad_norm": 0.07051674276590347,
+      "learning_rate": 2.8042870443057812e-05,
+      "loss": 0.4904,
+      "step": 56
+    },
+    {
+      "epoch": 2.7142857142857144,
+      "grad_norm": 0.08204561471939087,
+      "learning_rate": 2.6179744029289542e-05,
+      "loss": 0.5739,
+      "step": 57
+    },
+    {
+      "epoch": 2.761904761904762,
+      "grad_norm": 0.07661724835634232,
+      "learning_rate": 2.4554215237845687e-05,
+      "loss": 0.6318,
+      "step": 58
+    },
+    {
+      "epoch": 2.8095238095238093,
+      "grad_norm": 0.08298637717962265,
+      "learning_rate": 2.3170891806693566e-05,
+      "loss": 0.4678,
+      "step": 59
+    },
+    {
+      "epoch": 2.857142857142857,
+      "grad_norm": 0.07713375240564346,
+      "learning_rate": 2.2033694916392002e-05,
+      "loss": 0.6443,
+      "step": 60
+    },
+    {
+      "epoch": 2.9047619047619047,
+      "grad_norm": 0.08164560794830322,
+      "learning_rate": 2.1145848075078993e-05,
+      "loss": 0.3579,
+      "step": 61
+    },
+    {
+      "epoch": 2.9523809523809526,
+      "grad_norm": 0.07253335416316986,
+      "learning_rate": 2.0509867981087663e-05,
+      "loss": 0.2406,
+      "step": 62
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 0.0779012143611908,
+      "learning_rate": 2.0127557389091428e-05,
+      "loss": 0.4525,
+      "step": 63
+    },
+    {
+      "epoch": 3.0,
+      "eval_loss": 0.4695841372013092,
+      "eval_runtime": 15.6701,
+      "eval_samples_per_second": 1.468,
+      "eval_steps_per_second": 0.191,
+      "step": 63
+    }
+  ],
+  "logging_steps": 1.0,
+  "max_steps": 63,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 0,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 5.4360679349905e+17,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}